Interactive listening evidence · Base & Medium

Vocal burst 21: Deep Breath, Resonant Hum

Gemini event spans versus independently predicted Base and Medium spans. Hear the clip and inspect both models’ event labels, 20 ms curves and 192 scores.

← All 50 examples ← Previous Next →

21. Deep Breath, Resonant Hum

k97_age4_bg0VFOCS__moderately_low__de.c003

vprof_original · de/synth · 6.80 s · validation split

2 Gemini eventsBase count 1.6Medium count 1.9

Source key: k97_age4_bg0__V__FOCS__moderately_low__de.c003 · Audio SHA256: 2a889e4396e0fc917b85c77fc324c7fcccb4685608b7d6776228643b2d72ed91

Gemini annotation · selection aid

0.05–0.88 s: Resonant Hum · group hum
1.95–2.50 s: Deep Breath · group breath_calm

Base predictions

20 ms frame probability; dashed line = 0.5 threshold

0.00–0.70 s: Hum 87%, Affirmative Grunt 6%, Exhausted Groan 1% · onset 0.99
0.10–0.76 s: Hum 84%, Affirmative Grunt 8%, Exhausted Groan 1% · onset 0.54
1.24–1.94 s: Breath 57%, Exasperated Sigh 8%, Sharp Inhale 6% · onset 0.75
1.40–2.14 s: Breath 53%, Exasperated Sigh 9%, Sharp Inhale 7% · onset 0.64
1.48–2.18 s: Breath 53%, Exasperated Sigh 9%, Sharp Inhale 7% · onset 0.84
1.54–2.20 s: Breath 52%, Exasperated Sigh 9%, Sharp Inhale 7% · onset 0.60
1.62–2.40 s: Breath 58%, Exasperated Sigh 9%, Sharp Inhale 5% · onset 0.73
1.74–2.42 s: Breath 57%, Exasperated Sigh 9%, Sharp Inhale 5% · onset 0.92
1.86–2.50 s: Breath 60%, Exasperated Sigh 8%, Sharp Inhale 5% · onset 0.74
1.98–2.56 s: Breath 64%, Exasperated Sigh 7%, Sharp Inhale 5% · onset 0.87
2.04–2.64 s: Breath 66%, Exasperated Sigh 6%, Sharp Inhale 4% · onset 0.67
2.14–2.68 s: Breath 66%, Exasperated Sigh 5%, Sharp Inhale 5% · onset 0.56
2.22–2.76 s: Breath 67%, Sharp Inhale 5%, Wistful Sigh 5% · onset 0.86
2.28–2.82 s: Breath 67%, Wistful Sigh 6%, Sharp Inhale 6% · onset 0.59
2.44–2.98 s: Breath 54%, Sharp Inhale 13%, Exasperated Sigh 7% · onset 0.60
2.50–3.02 s: Breath 48%, Sharp Inhale 17%, Exasperated Sigh 7% · onset 0.58

Frame-positive regions: 1 · CPS 10.80 · Orange timbre cosine 0.899 · identity cosine 0.839

Medium predictions

20 ms frame probability; dashed line = 0.5 threshold

0.04–0.66 s: Hum 93%, Affirmative Grunt 1%, Other / rare burst 1% · onset 0.99
0.80–1.56 s: Breath 48%, Sharp Inhale 8%, Exasperated Sigh 7% · onset 0.54
0.94–1.62 s: Breath 44%, Sharp Inhale 9%, Exasperated Sigh 7% · onset 0.59
1.10–1.78 s: Breath 44%, Sharp Inhale 9%, Exasperated Sigh 8% · onset 0.55
1.24–1.94 s: Breath 47%, Sharp Inhale 9%, Exasperated Sigh 7% · onset 0.61
1.34–1.98 s: Breath 43%, Sharp Inhale 10%, Exasperated Sigh 8% · onset 0.52
1.50–2.24 s: Breath 48%, Sharp Inhale 8%, Exasperated Sigh 8% · onset 0.66
1.60–2.24 s: Breath 48%, Sharp Inhale 9%, Exasperated Sigh 8% · onset 0.69
1.66–2.34 s: Breath 48%, Sharp Inhale 8%, Exasperated Sigh 8% · onset 0.64
1.74–2.40 s: Breath 55%, Sharp Inhale 7%, Exasperated Sigh 7% · onset 0.64
1.84–2.46 s: Breath 54%, Contented Sigh 7%, Sharp Inhale 7% · onset 0.70
1.96–2.48 s: Breath 53%, Contented Sigh 7%, Sharp Inhale 6% · onset 0.71
2.02–2.64 s: Breath 59%, Contented Sigh 7%, Wistful Sigh 6% · onset 0.72
2.10–2.68 s: Breath 54%, Wistful Sigh 7%, Contented Sigh 7% · onset 0.55
2.22–2.76 s: Breath 50%, Wistful Sigh 12%, Contented Sigh 6% · onset 0.74
2.36–2.88 s: Breath 54%, Wistful Sigh 16%, Sharp Inhale 5% · onset 0.53

Frame-positive regions: 6 · CPS 11.01 · Orange timbre cosine 0.930 · identity cosine 0.825

All 192 scalar scores: Base and Medium raw plus reference z

Target	Base raw	Base z	Medium raw	Medium z
`emo_Affection`	0.61	1.06	0.36	0.62
`emo_Amusement`	0.17	0.19	0.10	0.11
`emo_Anger`	0.04	0.06	0.05	0.08
`emo_Astonishment_Surprise`	0.04	0.05	-0.02	-0.04
`emo_Awe`	0.17	0.40	0.13	0.30
`emo_Bitterness`	0.04	0.08	0.07	0.13
`emo_Concentration`	2.11	2.00	2.12	2.00
`emo_Confusion`	0.01	0.02	0.03	0.05
`emo_Contemplation`	2.97	4.83	2.86	4.65
`emo_Contempt`	-0.00	-0.01	0.05	0.10
`emo_Contentment`	1.93	3.75	1.61	3.14
`emo_Disappointment`	0.16	0.23	0.18	0.25
`emo_Disgust`	-0.01	-0.03	0.04	0.06
`emo_Distress`	0.13	0.16	0.16	0.19
`emo_Doubt`	0.18	0.37	0.26	0.54
`emo_Elation`	0.01	0.00	0.01	-0.01
`emo_Embarrassment`	0.01	-0.07	-0.00	-0.10
`emo_Emotional_Numbness`	0.52	0.56	0.76	0.82
`emo_Fatigue_Exhaustion`	0.70	1.25	0.71	1.27
`emo_Fear`	0.06	0.07	0.03	0.03
`emo_Helplessness`	0.23	0.34	0.17	0.25
`emo_Hope_Enthusiasm_Optimism`	0.88	1.00	0.63	0.68
`emo_Impatience_and_Irritability`	0.06	-0.13	0.03	-0.17
`emo_Infatuation`	0.03	0.07	-0.02	-0.00
`emo_Interest`	1.61	0.02	1.56	-0.03
`emo_Intoxication_Altered_States_of_Consciousness`	0.01	0.06	0.04	0.11
`emo_Jealousy_and_Envy`	-0.02	-0.18	-0.02	-0.17
`emo_Longing`	0.54	0.72	0.55	0.73
`emo_Malevolence_Malice`	0.01	-0.08	0.05	-0.01
`emo_Pain`	0.07	0.13	0.05	0.09
`emo_Pleasure_Ecstasy`	0.07	0.08	0.05	0.06
`emo_Pride`	0.33	0.65	0.36	0.71
`emo_Relief`	0.40	0.54	0.24	0.30
`emo_Sadness`	0.15	0.20	0.23	0.30
`emo_Sexual_Lust`	0.00	-0.06	-0.01	-0.08
`emo_Shame`	-0.03	-0.09	-0.01	-0.05
`emo_Sourness`	0.00	0.02	0.07	0.17
`emo_Teasing`	0.02	0.03	0.03	0.06
`emo_Thankfulness_Gratitude`	0.13	0.13	0.09	0.07
`emo_Triumph`	0.03	0.06	0.04	0.09
`vn_AGEV_reg`	3.46	0.38	3.47	0.39
`vn_AROU_reg`	1.49	-0.76	1.36	-0.87
`vn_ARSH_reg`	2.88	0.35	2.66	0.09
`vn_ATCK_reg`	2.52	0.28	2.36	0.16
`vn_BKGN_reg`	3.90	1.57	3.94	1.63
`vn_BRGT_reg`	2.70	0.88	2.61	0.76
`vn_CHNK_reg`	2.61	0.62	2.59	0.60
`vn_CLRT_reg`	4.00	2.09	4.04	2.14
`vn_COGL_reg`	0.79	-1.23	1.40	-0.65
`vn_DARC_reg`	2.68	0.77	2.76	0.83
`vn_DFLU_reg`	0.51	-1.67	0.33	-1.82
`vn_EMPH_reg`	2.88	0.18	2.89	0.18
`vn_ESTH_reg`	4.04	2.10	3.94	1.97
`vn_EXPL_reg`	0.04	-0.15	0.03	-0.17
`vn_FOCS_reg`	3.73	1.26	3.53	1.08
`vn_FULL_reg`	3.67	2.13	3.73	2.19
`vn_GEND_reg`	4.80	0.47	4.74	0.43
`vn_HARM_reg`	3.34	1.03	3.30	0.98
`vn_METL_reg`	1.05	-0.59	1.03	-0.62
`vn_RANG_reg`	1.80	-1.24	1.66	-1.40
`vn_RCQL_reg`	4.11	1.53	4.12	1.53
`vn_REGS_reg`	1.35	0.12	1.26	0.05
`vn_RESP_reg`	2.25	-0.40	2.19	-0.46
`vn_ROUG_reg`	2.32	0.32	2.13	0.11
`vn_R_CHST_reg`	3.92	2.11	3.77	1.94
`vn_R_HEAD_reg`	1.45	-0.86	1.40	-0.91
`vn_R_MASK_reg`	2.45	0.54	2.42	0.51
`vn_R_MIXD_reg`	3.47	2.42	3.55	2.51
`vn_R_NASL_reg`	1.67	-1.07	1.50	-1.24
`vn_R_ORAL_reg`	3.28	1.48	3.16	1.32
`vn_R_THRT_reg`	3.06	1.23	2.97	1.13
`vn_SMTH_reg`	3.70	1.43	3.80	1.52
`vn_STNC_reg`	2.97	0.29	3.13	0.44
`vn_STRU_reg`	4.08	2.03	4.20	2.15
`vn_S_ASMR_reg`	1.76	0.28	1.89	0.37
`vn_S_AUTH_reg`	2.70	1.55	2.86	1.70
`vn_S_CART_reg`	0.02	-1.10	0.31	-0.89
`vn_S_CASU_reg`	2.12	-1.31	2.24	-1.22
`vn_S_CONV_reg`	2.78	0.14	2.84	0.19
`vn_S_DRAM_reg`	1.60	-0.98	1.93	-0.69
`vn_S_FORM_reg`	2.39	1.17	2.81	1.58
`vn_S_MONO_reg`	3.42	0.47	3.48	0.51
`vn_S_NARR_reg`	3.27	1.36	3.28	1.36
`vn_S_NEWS_reg`	1.08	1.18	1.04	1.12
`vn_S_PLAY_reg`	0.21	-1.63	0.25	-1.60
`vn_S_RANT_reg`	0.01	-0.93	0.10	-0.86
`vn_S_STRY_reg`	2.28	-0.15	2.35	-0.10
`vn_S_TECH_reg`	2.02	1.12	2.01	1.11
`vn_S_WHIS_reg`	1.13	-0.29	1.14	-0.28
`vn_TEMP_reg`	2.45	0.28	2.38	0.22
`vn_TENS_reg`	1.73	0.20	1.77	0.25
`vn_VALN_reg`	2.93	0.54	3.06	0.65
`vn_VALS_reg`	3.33	0.75	3.20	0.63
`vn_VFLX_reg`	3.00	0.62	2.73	0.39
`vn_VOLT_reg`	0.99	-1.80	0.83	-1.99
`vn_VULN_reg`	1.95	-0.70	1.70	-0.96
`vn_WARM_reg`	4.03	1.60	3.80	1.34
`genuineness_0_6`	4.73	1.48	4.68	1.45
`blend_0_10`	7.88	0.44	7.97	0.47
`R_quality`	0.66	-1.29	0.73	-1.09
`eiv_extra:Age`	3.29	0.14	3.33	0.27
`eiv_extra:Arousal`	0.78	-1.18	0.75	-1.24
`eiv_extra:Authenticity`	2.76	0.63	2.78	0.71
`eiv_extra:Background_Noise`	0.32	-1.85	0.28	-2.00
`eiv_extra:Confident_vs._Hesitant`	1.06	0.08	1.02	-0.05
`eiv_extra:Gender`	-0.59	0.03	-0.22	0.40
`eiv_extra:High-Pitched_vs._Low-Pitched`	1.87	0.18	1.65	-0.70
`eiv_extra:Monotone_vs._Expressive`	1.43	-0.92	1.25	-1.29
`eiv_extra:Recording_Quality`	2.25	0.33	2.23	0.27
`eiv_extra:Serious_vs._Humorous`	0.83	-0.28	0.82	-0.32
`eiv_extra:Soft_vs._Harsh`	0.68	1.23	0.63	1.10
`eiv_extra:Submissive_vs._Dominant`	0.40	0.08	0.28	-0.30
`eiv_extra:Valence`	0.00	-0.01	0.02	0.05
`eiv_extra:Vulnerable_vs._Emotionally_Detached`	1.66	-0.11	1.59	-0.29
`eiv_extra:Warm_vs._Cold`	0.11	0.20	0.07	0.07
`eiv_extra:score_background_quality`	3.86	0.81	3.82	0.74
`eiv_extra:score_content_enjoyment`	4.63	0.39	4.69	0.60
`eiv_extra:score_overall_quality`	3.01	0.70	3.05	0.78
`eiv_extra:score_speech_quality`	1.95	1.00	1.98	1.22
`audiobox:CE`	5.64	0.83	5.73	0.91
`audiobox:CU`	6.80	1.15	6.68	1.03
`audiobox:PC`	1.58	-0.46	1.69	-0.40
`audiobox:PQ`	7.93	1.01	7.93	1.01
`dnsmos:SIG_raw`	4.20	0.46	4.26	0.54
`dnsmos:BAK_raw`	4.54	1.18	4.58	1.22
`dnsmos:OVRL_raw`	4.01	1.13	4.04	1.18
`dnsmos:SIG`	3.65	0.32	3.69	0.40
`dnsmos:BAK`	4.19	0.86	4.25	0.93
`dnsmos:OVRL`	3.42	0.96	3.46	1.03
`dnsmos:P808_MOS`	3.74	0.64	3.80	0.77
`burst_count_log1p`	0.97	1.50	1.05	1.62
`voiceclap_attribute:Affection`	0.13	-1.48	0.39	-1.00
`voiceclap_attribute:Age`	3.41	0.33	3.42	0.35
`voiceclap_attribute:Amusement`	0.08	-0.54	0.00	-0.68
`voiceclap_attribute:Anger`	0.13	-1.70	0.11	-1.75
`voiceclap_attribute:Arousal`	0.54	-1.42	0.74	-1.08
`voiceclap_attribute:Astonishment_Surprise`	-0.08	-1.23	-0.34	-1.76
`voiceclap_attribute:Authenticity`	2.77	-0.02	2.81	0.22
`voiceclap_attribute:Awe`	0.10	-1.69	0.22	-1.23
`voiceclap_attribute:Background_Noise`	0.30	-1.01	0.25	-1.19
`voiceclap_attribute:Bitterness`	0.10	-2.07	0.09	-2.14
`voiceclap_attribute:Concentration`	2.00	1.48	2.11	1.68
`voiceclap_attribute:Confident_vs._Hesitant`	1.09	0.05	1.18	0.23
`voiceclap_attribute:Confusion`	0.10	-1.62	-0.10	-2.22
`voiceclap_attribute:Contemplation`	2.27	3.67	2.52	4.29
`voiceclap_attribute:Contempt`	0.07	-1.89	0.04	-1.99
`voiceclap_attribute:Contentment`	1.52	3.02	1.58	3.23
`voiceclap_attribute:Disappointment`	0.14	-2.12	0.15	-2.09
`voiceclap_attribute:Disgust`	-0.01	-3.08	-0.06	-3.29
`voiceclap_attribute:Distress`	0.08	-2.41	-0.05	-2.80
`voiceclap_attribute:Doubt`	0.50	-0.17	0.56	0.13
`voiceclap_attribute:Elation`	-0.04	-1.46	-0.08	-1.57
`voiceclap_attribute:Embarrassment`	-0.10	-1.30	-0.04	-1.10
`voiceclap_attribute:Emotional_Numbness`	0.16	-1.88	0.25	-1.55
`voiceclap_attribute:Fatigue_Exhaustion`	0.75	1.10	0.67	0.82
`voiceclap_attribute:Fear`	-0.19	-3.82	-0.12	-3.49
`voiceclap_attribute:Gender`	-0.24	-0.09	-0.36	-0.21
`voiceclap_attribute:Helplessness`	0.13	-1.97	0.16	-1.85
`voiceclap_attribute:High-Pitched_vs._Low-Pitched`	1.51	-0.88	1.57	-0.71
`voiceclap_attribute:Hope_Enthusiasm_Optimism`	0.64	-0.16	0.65	-0.14
`voiceclap_attribute:Impatience_and_Irritability`	0.17	-1.63	0.05	-1.85
`voiceclap_attribute:Infatuation`	0.01	-1.79	0.14	-1.42
`voiceclap_attribute:Interest`	1.55	-0.12	1.62	0.04
`voiceclap_attribute:Intoxication_Altered_States_of_Consciousness`	0.08	-0.91	-0.12	-1.34
`voiceclap_attribute:Jealousy_&_Envy`	0.01	-2.10	0.00	-2.13
`voiceclap_attribute:Longing`	0.17	-1.67	0.33	-0.93
`voiceclap_attribute:Malevolence_Malice`	0.04	-2.29	0.06	-2.24
`voiceclap_attribute:Monotone_vs._Expressive`	1.05	-1.22	1.24	-0.90
`voiceclap_attribute:Pain`	-0.04	-1.92	-0.03	-1.90
`voiceclap_attribute:Pleasure_Ecstasy`	0.05	-1.52	0.12	-1.28
`voiceclap_attribute:Pride`	0.47	-0.90	0.34	-1.26
`voiceclap_attribute:Recording_Quality`	2.37	0.17	2.44	0.40
`voiceclap_attribute:Relief`	0.23	-1.91	0.32	-1.69
`voiceclap_attribute:Sadness`	0.04	-2.26	0.09	-2.11
`voiceclap_attribute:Serious_vs._Humorous`	0.75	-0.09	0.62	-0.32
`voiceclap_attribute:Sexual_Lust`	0.06	-1.37	0.09	-1.29
`voiceclap_attribute:Shame`	-0.06	-2.08	0.09	-1.53
`voiceclap_attribute:Soft_vs._Harsh`	0.40	0.68	0.41	0.71
`voiceclap_attribute:Sourness`	0.11	-2.03	0.14	-1.94
`voiceclap_attribute:Submissive_vs._Dominant`	0.37	-0.70	0.34	-0.80
`voiceclap_attribute:Teasing`	0.09	-1.18	0.05	-1.29
`voiceclap_attribute:Thankfulness_Gratitude`	0.02	-2.58	0.04	-2.53
`voiceclap_attribute:Triumph`	0.06	-1.83	-0.04	-2.11
`voiceclap_attribute:Valence`	-0.07	-0.09	0.08	0.14
`voiceclap_attribute:Vulnerable_vs._Emotionally_Detached`	1.69	0.08	1.63	-0.02
`voiceclap_attribute:Warm_vs._Cold`	0.04	0.27	0.11	0.43
`voiceclap_attribute:duration`	7.31	-0.57	7.11	-0.60
`voiceclap_attribute:score_background_quality`	3.58	0.67	3.53	0.58
`voiceclap_attribute:score_content_enjoyment`	4.65	-0.07	4.65	-0.04
`voiceclap_attribute:score_overall_quality`	2.86	0.55	2.85	0.51
`voiceclap_attribute:score_speech_quality`	1.94	0.75	1.92	0.43
`voiceclap_attribute:talking_speed`	8.97	-0.02	8.69	-0.09

← All 50 examples ← Previous Next →